A multi-lane diversion control method, device and medium

Abstract

The embodiments of this specification disclose a multi-lane diversion control method, device, and medium, which are applied in the field of intelligent transportation technology to solve the problems of low efficiency and low accuracy of existing diversion methods. The method includes: dividing monitoring sub-regions based on road network data, and using historical vehicle travel data to determine the topological connection data of each sub-region. Identifying the target traffic characteristics of each sub-region through cluster analysis, and determining the corresponding diversion traffic regions accordingly. Identifying the current congested road sections and congestion directions based on real-time vehicle travel data, and formulating a diversion strategy in combination with the conditions of the diversion traffic regions. Inputting the passing speed of the current congested road section, the travel data of the diversion traffic region, and the diversion strategy into a preset traffic flow prediction model, and adjusting the diversion strategy according to the model output to achieve dynamic diversion control.

Description

Technical Field

[0001] This specification relates to the technical field of intelligent transportation, and particularly to a multi-lane traffic diversion control method, device, and medium. Background Art

[0002] With the accelerating urbanization process and the continuous increase in the number of motor vehicles, the problem of urban traffic congestion is deteriorating at an unprecedented rate, becoming a thorny issue restricting the improvement of urban operation efficiency and residents' quality of life. Especially during the morning and evening rush hours and in bustling areas such as commercial centers and transportation hubs, traffic congestion is particularly prominent, bringing a heavy burden to the daily operation of the city. Traffic congestion not only prolongs the commuting time of citizens, increases travel costs, but also seriously affects the city's logistics transportation and the response speed of emergency services. Vehicles staying in congested sections for a long time not only consume a large amount of fuel resources, exacerbate air pollution, but also greatly reduce the overall operation efficiency of the urban traffic network. In addition, long waiting times and unsmooth driving are likely to cause driver fatigue and anxiety, increasing the risk of traffic accidents and posing a potential threat to public safety. Therefore, traffic diversion that alleviates urban traffic congestion and improves road capacity is of great significance to daily traffic.

[0003] Currently, traditional traffic management methods often rely on manual intervention and static traffic signal control. Due to the lack of in-depth analysis of road network data and relying on manual experience for traffic diversion control, it is difficult to accurately divide the monitored sub-areas and accurately identify the traffic characteristics of each area, and it is difficult to adapt to complex traffic flow changes and real-time road conditions. Therefore, it is difficult to alleviate traffic congestion problems during peak hours. In addition, relying on fixed traffic signal control methods, lacking dynamic adjustment capabilities and being unable to perform dynamic traffic diversion based on actual situations, the efficiency of traffic diversion control is relatively low. Moreover, when formulating traffic diversion strategies, existing traffic diversion control methods often only consider single path or time factors, lacking comprehensive consideration and making it difficult to continuously optimize traffic diversion control. Summary of the Invention

[0004] To solve the above technical problems, one or more embodiments of this specification provide a multi-lane traffic diversion control method, device, and medium.

[0005] One or more embodiments of this specification adopt the following technical solutions:

[0006] One or more embodiments of this specification provide a multi-lane traffic diversion control method, the method comprising:

[0007] Dividing the current monitored area based on road network related data to obtain multiple monitored sub-areas, and determining the topological connection data corresponding to each monitored sub-area according to the historical vehicle driving data of each monitored sub-area;

[0008] Perform clustering analysis on each of the monitored sub-regions according to the topological connection data, determine the target traffic characteristics of each of the monitored sub-regions, and determine the diversion traffic regions corresponding to each of the monitored sub-regions based on the target traffic characteristics;

[0009] Determine the current congested road sections according to the current vehicle driving data of each monitored sub-region, and calculate the passing speeds of each lane in each direction within the current congested road sections, so as to divide and determine the congested direction and the non-congested direction;

[0010] Determine the diversion traffic region corresponding to the current congested road section, and determine the corresponding diversion strategy according to the passing speeds of the congested direction and the non-congested direction and the current vehicle driving data of the corresponding diversion traffic region; wherein, the diversion strategy includes: diversion path, diversion time;

[0011] Input the passing speeds of each lane of the current congested road section, the current vehicle driving data of the corresponding diversion traffic region, and the diversion strategy into a preset traffic flow prediction model, so as to adjust the diversion strategy based on the output result for diversion control.

[0012] Optionally, in one or more embodiments of the present specification, dividing the current monitoring region based on road network related data to obtain multiple monitored sub-regions specifically includes:

[0013] Based on multiple data interfaces, obtain the road network related data of the current monitoring region; wherein, the road network related data includes: basic road network data, detector detection data, road operation data;

[0014] According to the traffic network structure corresponding to the basic road network data and the preset regional boundary conditions, determine the initial monitored sub-regions of multiple traffic levels corresponding to the current monitoring region; wherein the traffic levels include: intersection layer, intercity expressway layer, suburban express layer, living area road layer; the preset regional boundary conditions include: urban area level data, urban geographical boundary data, monitoring area limit data;

[0015] Match the position information corresponding to the detector detection data and the operation data with the basic road network data, so as to divide the detector detection data and the operation data into the corresponding initial monitored sub-regions;

[0016] Based on the detector detection data and the operation data, determine the internal traffic flow of each of the initial monitored sub-regions, and dynamically adjust the jurisdiction scope of the initial monitored sub-regions according to the internal traffic flow to obtain multiple monitored sub-regions.

[0017] Optionally, in one or more embodiments of the present specification, according to the historical vehicle driving data of each of the monitored sub-regions, determining the topological connection data corresponding to each of the monitored sub-regions specifically includes:

[0018] Obtaining the historical vehicle driving data of each of the monitored sub-regions, and based on the driving direction data corresponding to each of the vehicle driving data and the boundary positions of each of the monitored sub-regions, identifying the incoming road sections and outgoing road sections of each of the monitored sub-regions;

[0019] Respectively taking the incoming road section and the outgoing road section as the traversal starting nodes, and based on the traversal starting nodes and a preset traversal direction, traversing each road section of the monitored sub-region to obtain an incoming road section sequence and an outgoing road section sequence, and taking each road section in the incoming road section sequence and the outgoing road section sequence as a node; wherein, the traversal direction is: clockwise or counterclockwise;

[0020] Determining the adjacent road sections of each of the nodes, and based on the basic road network data corresponding to the adjacent road sections, determining the road section types of each of the nodes; wherein, the road section types include: diversion type, confluence type;

[0021] According to the historical vehicle driving data of each of the nodes, determining the vehicle driving frequency and the vehicle driving quantity between each of the nodes, and according to the vehicle driving frequency, the vehicle driving quantity and the road section type, determining the connection strength of each node;

[0022] Based on the connection strength corresponding to each of the nodes and the sequence name corresponding to the nodes, determining the connection paths between each of the constructed nodes, and obtaining the topological connection data corresponding to each of the monitored sub-regions.

[0023] Optionally, in one or more embodiments of the present specification, performing clustering analysis on each of the monitored sub-regions according to the topological connection data, and determining the target traffic characteristics of each of the monitored sub-regions specifically includes:

[0024] Based on the topological connection data, determining the adjacent nodes of each node in the monitored sub-region to construct a neighbor node set corresponding to each node;

[0025] Sequentially obtaining the adjacent nodes corresponding to each adjacent node in the neighbor node set, and based on the intersection of the neighbor node set and the adjacent nodes corresponding to each adjacent node, determining the common neighbor nodes corresponding to the node and the adjacent node of the node;

[0026] Based on the historical vehicle driving data corresponding to the adjacent nodes and the common neighbor nodes of each of the nodes, constructing a feature vector corresponding to each of the nodes;

[0027] Perform similarity clustering based on the feature vectors corresponding to each of the nodes to obtain multiple clustering clusters, and extract the common features of the nodes within each clustering cluster;

[0028] Summarize the common features of each clustering cluster and determine the corresponding location distribution of each clustering cluster, so as to determine the target traffic features of each monitoring sub-region based on the common features of each clustering cluster and the corresponding location distribution.

[0029] Optionally, in one or more embodiments of this specification, determining a diversion traffic region corresponding to each monitoring sub-region based on the target traffic features specifically includes:

[0030] Based on the target traffic features of each monitoring sub-region, identify the traffic bottleneck data of each monitoring sub-region; wherein, the traffic bottleneck data includes: traffic peak period, congestion node range, road capacity;

[0031] According to the traffic bottleneck data corresponding to each monitoring sub-region, determine the diversion capacity data corresponding to each monitoring sub-region; wherein, the diversion capacity data includes: diversion time, diversion capacity;

[0032] Based on the diversion capacity data corresponding to the adjacent monitoring sub-regions of the monitoring sub-region, determine an optional diversion traffic region where the diversion time corresponds to the traffic peak period;

[0033] Determine the diversion capacity value of each optional diversion traffic region according to the diversion capacity of each optional diversion traffic region, so as to determine the diversion traffic region corresponding to each monitoring sub-region based on the diversion capacity value.

[0034] Optionally, in one or more embodiments of this specification, determine a diversion traffic region corresponding to the current congested road section, and determine a corresponding diversion strategy according to the passing speeds of the congested direction and the non-congested direction and the current vehicle driving data of the corresponding diversion traffic region, specifically including:

[0035] According to the diversion traffic region corresponding to the monitoring sub-region where the current congested road section is located, determine multiple traffic regions to be diverted, and filter the multiple traffic regions to be diverted according to the incoming road section or the outgoing road section within the preset range of the current congested road section to obtain the diversion traffic region corresponding to the current congested road section;

[0036] Based on the current vehicle driving data of the incoming road section and the outgoing road section corresponding to the non-congested direction within the diversion traffic region, determine the number of vehicles waiting to enter relatively in the non-congested direction;

[0037] Determine the length of the waitable time in the non-congested direction based on the passing speed in the non-congested direction and the data of the relative waiting vehicles to enter;

[0038] Based on the passing speed in the congested direction and the current vehicle driving data of the incoming section and the outgoing section corresponding to the non-congested direction in the diversion traffic area, determine the growth speed of the congestion queue in the congested direction;

[0039] Determine the passing time ratio in the congested direction according to the growth speed of the congestion queue, the length of the waitable time, and the road section space information in the non-congested direction;

[0040] If the passing time ratio is greater than a preset threshold, enable the alternative route corresponding to the congested direction in the diversion traffic area.

[0041] Optionally, in one or more embodiments of this specification, before inputting the passing speed of each lane of the current congested road section, the current vehicle driving data of the corresponding diversion traffic area, and the diversion strategy into the preset traffic flow prediction model, the method further includes:

[0042] Collect the historical vehicle driving data corresponding to the historical diversion strategies in the current monitoring area, and divide the historical vehicle driving data corresponding to the historical diversion strategies based on a preset ratio to obtain training set data and validation set data;

[0043] Input the training set data into the initial time series model for iterative training to obtain the trained time series model;

[0044] Evaluate the trained time series model based on the validation set data, and adjust the trained time series model according to the evaluation result to obtain the preset traffic flow prediction model.

[0045] Optionally, in one or more embodiments of this specification, based on the output result, adjust the diversion strategy for diversion control, specifically including:

[0046] If it is determined that the traffic flow is in a downward trend based on the output result, determine to maintain the diversion strategy for the current congested road section;

[0047] If it is determined that the traffic flow is in an upward trend, determine the current passing time ratio corresponding to the current diversion strategy;

[0048] If the current passing time ratio is less than the preset threshold, gradually increase the current passing time and adjust the diversion strategy for diversion control;

[0049] If the current passing time ratio is greater than the preset threshold, determine the alternative sections corresponding to each outgoing section in the congested direction;

[0050] Based on the distances between the alternative sections and the congested section and the traffic flows of the alternative sections, determine the activation order of the alternative sections to sequentially activate the alternative sections for traffic diversion.

[0051] One or more embodiments of this specification provide a traffic diversion control device for multiple lanes. The device includes:

[0052] At least one processor; and,

[0053] A memory communicatively connected to the at least one processor; wherein,

[0054] The memory stores instructions executable by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to: execute any of the above-mentioned methods.

[0055] A non-volatile computer storage medium provided by one or more embodiments of this specification stores computer-executable instructions, and the computer-executable instructions are configured to be able to: execute any of the above-mentioned methods.

[0056] The above-mentioned at least one technical solution adopted by the embodiments of this specification can achieve the following beneficial effects:

[0057] Based on historical and real-time data, determine traffic characteristics through cluster analysis, intelligently formulate traffic diversion strategies, and dynamically adjust the strategies according to the output results of the traffic flow prediction model, which can more effectively address traffic congestion problems and improve road traffic efficiency. By carefully dividing the monitoring area, the refinement of traffic management is realized, and congested sections can be quickly identified and responded to, improving the efficiency of traffic guidance. Considering comprehensively the passing speeds in the congested direction and the non-congested direction and the vehicle driving data in the traffic diversion area, precise traffic diversion paths and diversion times are formulated, and the road space in the non-congested direction can be used to effectively relieve the traffic pressure in the congested direction, improving the utilization rate of the road. In addition, the optimization method based on the prediction model can more accurately predict future traffic conditions, so as to formulate more reasonable traffic diversion strategies and achieve more effective traffic diversion control. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in this specification. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. In the drawings:

[0059] Figure 1 A flowchart of a multi-lane diversion control method provided by an embodiment of this specification;

[0060] Figure 2 A structural diagram of a multi-lane diversion control device provided by an embodiment of this specification;

[0061] Figure 3 A structural diagram of a non-volatile storage medium provided by an embodiment of this specification. Detailed implementation manners

[0062] Embodiments of this specification provide a multi-lane diversion control method, device, and medium.

[0063] To enable those skilled in the art to better understand the technical solutions in this specification, the following will clearly and completely describe the technical solutions in the embodiments of this specification with reference to the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on the embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this specification.

[0064] As Figure 1 shown, embodiments of this specification provide a flowchart of a multi-lane diversion control method. As Figure 1 can be seen, in one or more embodiments of this specification, a multi-lane diversion control method includes:

[0065] S101: Divide the current monitoring area based on road network related data to obtain multiple monitoring sub-areas, and determine the topological connection data corresponding to each monitoring sub-area according to the historical vehicle driving data of each monitoring sub-area.

[0066] In a large urban traffic network, the road network structure is complex and the traffic flow is large, making it difficult to directly manage and optimize the entire road network. Therefore, in the embodiments of this specification, in order to decompose complex traffic control tasks to improve the efficiency of diversion control, the current monitoring area is divided according to road network related data to obtain multiple monitoring sub-areas. Then, according to the historical vehicle driving data of each monitoring sub-area, the topological connection data corresponding to each monitoring sub-area is determined. By determining the topological connection data, the traffic connections and mutual influences between monitoring sub-areas can be obtained, which helps to formulate more accurate diversion strategies.

[0067] Specifically, in one or more embodiments of the present specification, the current monitoring area is divided into multiple monitoring sub-areas based on road network related data, which specifically includes the following process:

[0068] First, based on multiple data interfaces, road network related data of the current monitoring area is obtained. It can be understood that the road network related data includes: basic road network data such as road center line data, road grade data, intersection information, road attribute information, ancillary facility information, etc.; detector detection data such as traffic flow data, vehicle speed data, vehicle type data, etc.; road operation data such as highway tolls, pontoon bridge tolls, bridge tolls, etc. Then, according to the traffic network structure corresponding to the basic road network data and the preset area boundary conditions, the initial monitoring sub-areas of multiple traffic levels corresponding to the current monitoring area are determined. The traffic levels include: intersection layer, intercity highway layer, suburban expressway layer, living area road layer; and the preset area boundary conditions include: urban area level data, urban geographical boundary data, monitoring area limit data. Then, according to the position information corresponding to the detector detection data and operation data, and the basic road network data are matched, so as to divide the detector detection data and operation data into the corresponding initial monitoring sub-areas. Then, based on the detector detection data and operation data, the internal traffic flow of each initial monitoring sub-area is determined, so as to dynamically adjust the jurisdiction scope of the initial monitoring sub-area according to the internal traffic flow, and obtain multiple monitoring sub-areas.

[0069] In this process, by means of multiple data interfaces, road network related data from different sources can be efficiently integrated, improving the comprehensiveness and accuracy of the data, and providing a solid foundation for subsequent analysis and processing. Matching the detector detection data and operation data with the basic road network data according to the position information can accurately divide these data into the corresponding initial monitoring sub-areas. Then, according to the traffic network structure corresponding to the basic road network data and combined with the preset area boundary conditions, the initial monitoring sub-areas of multiple traffic levels corresponding to the current monitoring area can be scientifically determined. This division method fully considers the actual situation of the road network and the monitoring requirements, improving the pertinence and effectiveness of the monitoring. Dividing the traffic levels into intersection layer, intercity highway layer, suburban expressway layer and living area road layer, etc., helps to conduct targeted monitoring and management of traffic conditions at different levels. In addition, dynamically adjusting the jurisdiction scope of the initial monitoring sub-area according to the change of traffic flow enables the monitoring sub-area to be flexibly adjusted according to the actual situation, avoiding the limitations that may be brought by a fixed monitoring area.

[0070] Further, in one or more embodiments of the present specification, according to the historical vehicle driving data of each monitoring sub-area, the topological connection data corresponding to each monitoring sub-area is determined, which specifically includes the following process:

[0071] First, in order to perform accurate analysis based on the actual traffic conditions and avoid errors caused by subjective judgment, the embodiments of this specification obtain the historical vehicle driving data of each monitoring sub-region, and identify the entry section and exit section of each monitoring sub-region based on the driving direction data corresponding to each vehicle driving data and the boundary positions of each monitoring sub-region. Then, the entry section and the exit section are respectively used as the starting nodes for traversal, and each section of the monitoring sub-region is traversed according to the starting nodes for traversal and the preset traversal direction to obtain the entry section sequence and the exit section sequence, and each section in the entry section sequence and the exit section sequence is used as a node. It should be noted that the traversal direction is: clockwise or counterclockwise. Determine the adjacent sections of each node, and thus determine the section type of each node according to the basic road network data corresponding to the adjacent sections; where the section type includes: split type, merge type. Then, according to the historical vehicle driving data of each node, determine the vehicle driving frequency and vehicle driving quantity between each node, and determine the connection strength of each node according to the vehicle driving frequency, vehicle driving quantity and section type. Based on the connection strength corresponding to each node and the sequence name corresponding to the node, determine the connection paths between the nodes, and obtain the topological connection data corresponding to each monitoring sub-region.

[0072] For example, in a certain application scenario, vehicle driving data of a monitored sub-region in the past period is extracted from a traffic monitoring system, including information such as the driving direction of the vehicle, timestamp, starting point, and ending point. According to the driving direction of the vehicle and the boundary position of the monitored sub-region, it is possible to determine which road sections are the incoming road sections for vehicles to enter the monitored sub-region and which road sections are the outgoing road sections for vehicles to leave the monitored sub-region. For example, if a vehicle's driving direction is from east to west and its starting point is on the east boundary of the monitored sub-region, then the road section it is on is the incoming road section; if a vehicle's driving direction is from west to east and its ending point is on the west boundary of the monitored sub-region, then the road section it is on is the outgoing road section. Then, select the incoming road section as the starting node for traversal and set the traversal direction to be clockwise. Starting from the incoming road section, traverse each road section within the monitored sub-region in clockwise order until returning to the outgoing road section. In this way, an incoming road section sequence is obtained. Similarly, an outgoing road section sequence can be obtained. During the traversal process, each road section can be regarded as a node, and for each node, its adjacent road sections can be determined according to the basic road network data. Based on the connection situation between adjacent road sections, the road section type of this node can be determined, such as the split type (multiple road sections merging into one road section) or the merge type (one road section splitting into multiple road sections). According to the historical vehicle driving data, count the vehicle driving frequency and the number of vehicles between each pair of nodes, that is, between adjacent road sections. Combining the road section type and the vehicle driving data, assign a connectivity strength value to each node. This value reflects the magnitude and stability of the traffic flow between the nodes. Then, based on the connectivity strength of each node and the sequence name, construct the connectivity paths between the nodes. These connectivity paths together constitute the topological connection data of the monitored sub-region, which describes the connection relationship and traffic flow characteristics between each road section within the monitored sub-region.

[0073] In the above process of obtaining the topological connection data corresponding to each monitored sub-region, by setting the starting node for traversal and the preset traversal direction, it is possible to systematically traverse all the road sections within the monitored sub-region, construct clear incoming road section sequences and outgoing road section sequences, which not only improves the analysis efficiency but also ensures the coherence and integrity between the road sections. According to the basic road network data corresponding to the adjacent road sections, this process can accurately classify the road section types, which helps to more accurately evaluate the mutual influence and potential conflict points between the road sections. In addition, the method of evaluating the connectivity strength between each pair of nodes by combining the road section type and the historical vehicle driving data not only considers the influence of the traffic flow but also considers the influence of the road section type on the traffic flow, thus providing a more comprehensive connectivity evaluation. Based on the connectivity strength of each node and the sequence name, this process can construct the topological connection data corresponding to the monitored sub-region, which not only helps to reveal the internal structure of the traffic network but also provides a scientific basis for subsequent traffic congestion alleviation, traffic accident prevention, and traffic resource optimization, etc.

[0074] S102: Perform clustering analysis on each of the monitored sub-regions according to the topological connection data, determine the target traffic characteristics of each of the monitored sub-regions, and determine the diversion traffic regions corresponding to each of the monitored sub-regions based on the target traffic characteristics.

[0075] In order to be able to determine the diversion traffic regions corresponding to each monitored sub-region, so as to carry out traffic control for the diversion traffic regions and alleviate the traffic congestion problem. In the embodiments of this specification, clustering analysis will be performed on each monitored sub-region according to the topological connection data, so as to determine the target traffic characteristics of each monitored sub-region. The target traffic characteristics are helpful for reasonably allocating traffic resources and determining the diversion traffic regions corresponding to the monitored sub-regions.

[0076] Specifically, in one or more embodiments of this specification, performing clustering analysis on each monitored sub-region according to the topological connection data and determining the target traffic characteristics of each monitored sub-region specifically includes the following process:

[0077] First, determine the adjacent nodes of each node in the monitored sub-region based on the topological connection data, so as to construct the set of neighbor nodes corresponding to each node. Then, sequentially obtain the adjacent nodes corresponding to each adjacent node in the set of neighbor nodes, and thus determine the common neighbor nodes corresponding to the node and the adjacent node of the node according to the intersection of the set of neighbor nodes and the adjacent nodes corresponding to each adjacent node. Based on the historical vehicle driving data corresponding to the adjacent nodes and the common neighbor nodes of each node, construct the feature vector corresponding to each node. Perform similarity clustering according to the feature vectors corresponding to each node to obtain multiple clustering clusters, and extract the common features of the nodes within each clustering cluster. Summarize the common features of each clustering cluster and determine the corresponding location distribution of each clustering cluster, so as to determine the target traffic characteristics of each monitored sub-region by combining the common features of each clustering cluster with the corresponding location distribution.

[0078] To facilitate the understanding of the above content, the following is an example. Suppose there is a certain traffic monitoring sub-region. First, based on the topological connection data, the adjacent nodes of each node are determined. For example, if node A is connected to nodes B, C, and D, then the set of neighbor nodes of node A is {B, C, D}. Then, successively obtain the adjacent nodes of the adjacent nodes in each set of neighbor nodes and find the intersection. Taking node A as an example: when the set of adjacent nodes of node B is {A, E, F}, the intersection of node B and the set of neighbor nodes {B, C, D} of node A is {B}, but since the intersection of non-self nodes is concerned, {B} should actually be excluded, and the intersection of {E, F} and {C, D} is considered, which is assumed to be an empty set; when the set of adjacent nodes of node C is {A, G, H}, the intersection of the set of adjacent nodes of node C and {B, C, D} is {A, C}, but {A} is also excluded, and the intersection of {G, H} and {B, D} is considered, which is assumed to be {G}; when the set of adjacent nodes of node D is {A, I, J}, the intersection of the set of adjacent nodes of node D and {B, C, D} is {A, D}, {A} is excluded, and the intersection of {I, J} and {B, C} is considered, which is assumed to be an empty set. Combining the above information, the common neighbor nodes of node A and its adjacent nodes B, C, and D can be determined. Then, based on the historical vehicle travel data corresponding to the adjacent nodes and common neighbor nodes of each node, a feature vector can be constructed. For example, for node A, the following features can be considered: the number of adjacent nodes, such as 3: B, C, D; the traffic flow with each adjacent node, such as the traffic flow with B is X, the traffic flow with C is Y, and the traffic flow with D is Z; the number of common neighbor nodes and the corresponding traffic flow, such as the traffic flow of the common neighbor G with C is W. Combining these features constitutes the feature vector of node A. Then, the similarity clustering algorithm can be used to cluster the nodes according to the feature vectors. Suppose two clusters are obtained after clustering: cluster 1 and cluster 2. For cluster 1, the common features of its internal nodes can be extracted, such as large traffic flow and mostly located on the main urban roads. Determine the location distribution of cluster 1, such as mainly distributed in the central urban area. Similarly, the common features and location distribution of cluster 2 can also be extracted. Finally, combining the common features and location distribution of each cluster to determine the target traffic features of each monitoring sub-region. For example: the target traffic features of monitoring sub-region 1, which includes cluster 1, are: large traffic flow, mostly located on the main roads, and prone to traffic congestion. The target traffic features of monitoring sub-region 2, which includes cluster 2, are: moderate traffic flow, mostly located on the secondary roads, and relatively stable traffic conditions.

[0079] In the process of determining the target traffic characteristics of each monitoring sub-region as described above, by constructing a set of neighbor nodes and determining common neighbor nodes, the complex relationships between nodes in the traffic network can be deeply explored, and the direct and indirect connections between nodes can be revealed. Further, by using historical vehicle travel data to construct feature vectors, each node not only considers its adjacent nodes but also takes into account the influence of common neighbor nodes, thus more comprehensively reflecting the traffic characteristics of the node. In addition, through the similarity clustering algorithm, nodes can be divided into multiple clustering clusters based on the similarity of feature vectors, so that nodes with similar traffic characteristics are grouped together. Extracting common features from the clustering clusters can accurately reflect the traffic characteristics of the nodes within the clustering cluster, and then determine the target traffic characteristics of each monitoring sub-region, which helps to formulate more targeted traffic management strategies and more reasonably control and regulate traffic diversion in the subsequent stage.

[0080] Further, in one or more embodiments of the present specification, determining a diversion traffic region corresponding to each monitoring sub-region based on the target traffic characteristics specifically includes the following process:

[0081] First, based on the target traffic characteristics of each monitoring sub-region obtained through the above process, identify the traffic bottleneck data of each monitoring sub-region. Among them, it can be understood that the traffic bottleneck data includes: data such as traffic peak periods, congested node ranges, and road capacities. Then, according to the traffic bottleneck data corresponding to each monitoring sub-region, determine the diversion capacity data corresponding to each monitoring sub-region. It should also be noted that the diversion capacity data includes: data such as diversion time and diversion capacity. Then, according to the diversion capacity data corresponding to the adjacent monitoring sub-regions of the monitoring sub-region, determine the optional diversion traffic regions whose diversion time corresponds to the traffic peak period. Determine the diversion capacity values of each optional diversion traffic region according to the diversion capacity of each optional diversion traffic region, so as to determine the diversion traffic region corresponding to each monitoring sub-region based on the diversion capacity values. By identifying the traffic bottleneck data of each monitoring sub-region, such as traffic peak periods, congested node ranges, and road capacities, the congestion points in urban traffic can be accurately located. Determining the diversion capacity data of each monitoring sub-region according to the traffic bottleneck data, including diversion time and diversion capacity, etc., helps to determine a reliable diversion strategy in the subsequent stage, effectively guiding the traffic flow from the congested area to other areas, thereby alleviating traffic pressure.

[0082] S103: Determine the current congested road section according to the current vehicle travel data of each monitoring sub-region, and calculate the passing speeds of each direction of multiple lanes within the current congested road section, so as to divide and determine the congested direction and the non-congested direction.

[0083] In order to determine the congested sections and congestion directions of each monitored sub-region in the current monitored area, in the embodiments of this specification, the current congested sections will be determined based on the current vehicle driving data of each monitored sub-region, so as to calculate the passing speeds in each direction of multiple lanes within the current congested sections. Furthermore, based on the passing speeds of each lane and each direction, the congestion directions and non-congestion directions of multiple lanes will be determined. Congestion is often accompanied by an increased risk of traffic accidents. By promptly identifying the congested sections and congestion directions, it helps to subsequently carry out targeted traffic diversion for the congested sections and congestion directions, thereby reducing the incidence of traffic accidents.

[0084] S104: Determine the diversion traffic area corresponding to the current congested section, so as to determine the corresponding diversion strategy according to the passing speeds of the congestion direction and the non-congestion direction and the current vehicle driving data of the corresponding diversion traffic area; wherein, the diversion strategy includes: diversion path, diversion time.

[0085] Based on the above steps S102 - S103, the diversion traffic area corresponding to the current congested section is determined, so as to determine the corresponding diversion strategy according to the passing speeds of the congestion direction and the non-congestion direction and the current vehicle driving data of the corresponding diversion traffic area. Among them, the diversion strategy includes the diversion path and the diversion time. In this process, by comprehensively considering the passing speeds of the congestion direction, the non-congestion direction, and the current vehicle driving data of the diversion area, the diversion path and diversion time can be flexibly determined, improving the diversion efficiency while ensuring the road utilization rate.

[0086] Specifically, in one or more embodiments of this specification, to determine the diversion traffic area corresponding to the current congested section, so as to determine the corresponding diversion strategy according to the passing speeds of the congestion direction and the non-congestion direction and the current vehicle driving data of the corresponding diversion traffic area, it specifically includes the following process:

[0087] First, determine multiple traffic diversion areas to be diverted according to the traffic diversion area corresponding to the monitoring sub-area where the current congested section is located, and filter the multiple traffic diversion areas to be diverted based on the incoming road section or the outgoing road section within the preset range of the current congested section to obtain the traffic diversion area corresponding to the current congested section. Then, determine the number of vehicles waiting to enter relatively in the non-congested direction according to the current vehicle driving data of the incoming road section and the outgoing road section corresponding to the non-congested direction within the traffic diversion area. For example: There is a traffic diversion area with two main directions: the congested direction and the non-congested direction. Assume that there is only one incoming road section (Road A) and one outgoing road section (Road B) corresponding to the non-congested direction. At this time, the vehicle driving data of the incoming road section is the number of vehicles entering per hour in the current time period: 100 vehicles / hour, and the average vehicle entering speed is 60 km / h. The vehicle driving data of the outgoing road section is the number of vehicles leaving per hour in the current time period: 90 vehicles / hour, and the average vehicle leaving speed is 70 km / h. At this time, the number of vehicles entering - the number of vehicles leaving = 100 - 90 = 10 vehicles / hour, which means that in the non-congested direction, there is a net inflow of 10 vehicles per hour, that is, the number of vehicles entering is greater than the number of vehicles leaving. Then, the outgoing road section can accommodate more vehicles leaving, but the incoming road section may accumulate vehicles due to slower speed. At this time, the number of vehicles waiting to enter relatively can be approximated as the cumulative amount of the difference between the number of vehicles entering and leaving within a certain period of time. For example, if the observation time is 1 hour, the number of vehicles waiting to enter relatively is 10 vehicles.

[0088] Then, based on the passing speed in the non-congested direction and the data of the vehicles waiting to enter relatively, determine the length of the available waiting time in the non-congested direction. For example, in a certain application scenario, the passing speed of a certain road section in the non-congested direction is 50 km / h. At this time, there are 15 vehicles waiting to enter this road section, and the average length of each vehicle is 5 meters. Then, the length of the road occupied by the waiting vehicles can be determined as follows: the length of the road occupied by the waiting vehicles = the number of vehicles × the average length of each vehicle = 15 × 5 = 75 meters. Then calculate the time required for the vehicles to pass through this road section. Since the passing speed is 50 km / h, it needs to be converted to meters per second for calculation: 50 km / h = 50 × 1000 meters / 3600 seconds ≈ 13.89 meters per second. Therefore, the time required for the vehicles to pass through 75 meters is: the required time = the length of the road ÷ the passing speed = 75 ÷ 13.89 ≈ 5.39 seconds. Obtain the starting interval of the vehicles. If the time interval for the vehicles to start passing through this road section in sequence is 1 second, then the time required for 15 vehicles to pass through can be determined as: the total time = the number of vehicles × (the passing time of each vehicle + the starting interval) = 15 × (5.39 + 1) = 15 × 6.39 = 95.85 seconds. By statistically comparing this time with the preset safety buffer time, the length of the available waiting time in the non-congested direction can be determined. It can be understood that this length of the available waiting time is a time window to ensure that the vehicles in the non-congested direction can pass smoothly without causing new congestion.

[0089] Then, based on the passing speed in the congested direction and the current vehicle driving data of the incoming section and the outgoing section corresponding to the non-congested direction in the traffic diversion area, determine the growth speed of the congestion queue in the congested direction, so as to determine the passing time ratio in the congested direction according to the growth speed of the congestion queue, the length of the available waiting time, and the road section space information in the non-congested direction. If this passing time ratio is greater than the preset threshold, then enable the alternative route corresponding to the congested direction in the traffic diversion area.

[0090] In this process, by analyzing multiple traffic diversion areas to be divided and filtering based on the data of the current congested road section, the effectiveness and pertinence of the diversion strategy are ensured. By accurately calculating the number of vehicles waiting to enter relatively and the length of the available waiting time in the non-congested direction, the road section space in the non-congested direction can be utilized more effectively. And according to the growth speed of the congestion queue, timely adjust the passing time ratio in the congested direction to ensure the balance of traffic flow.

[0091] S105: Input the passing speeds of each lane of the current congested road section, the current vehicle driving data of the corresponding traffic diversion area, and the diversion strategy into a preset traffic flow prediction model, so as to adjust the diversion strategy for diversion control based on the output result.

[0092] After obtaining the diversion strategy through the above steps and performing diversion, in order to be able to adjust the diversion strategy in real time based on the traffic conditions for diversion control. In the embodiments of this specification, the passing speeds of each lane of the current congested section, the current vehicle driving data of the corresponding diversion traffic area, and the diversion strategy are input into a preset traffic flow prediction model, so as to adjust the diversion strategy for diversion control according to the output result. In this process, the traffic flow prediction model can output prediction results in real time according to the input data, and these results reflect the traffic flow trend in a future period of time. According to the prediction results, the diversion strategy can be dynamically adjusted to adapt to the changes in traffic conditions and ensure the effectiveness and flexibility of the diversion control measures.

[0093] Specifically, in one or more embodiments of this specification, before inputting the passing speeds of each lane of the current congested section, the current vehicle driving data of the corresponding diversion traffic area, and the diversion strategy into the preset traffic flow prediction model, the method further includes the following process:

[0094] First, collect the historical vehicle driving data corresponding to the historical diversion strategies in the current monitoring area, and divide the historical vehicle driving data corresponding to the historical diversion strategies based on a preset ratio to obtain training set data and validation set data. Input the training set data into the initial time series model for iterative training to obtain the trained time series model. Then evaluate the trained time series model based on the validation set data, and adjust the trained time series model according to the evaluation result to obtain the preset traffic flow prediction model. In this process, by using a large amount of historical vehicle driving data as the training set, the time series model can learn the historical patterns and trends of traffic flow. And the method of using the training set data and the validation set data to train and adjust the time series model to obtain the preset traffic flow prediction model improves the prediction accuracy.

[0095] Furthermore, in one or more embodiments of this specification, based on the output result, adjusting the diversion strategy for diversion control specifically includes the following process:

[0096] If it is determined according to the output result that the traffic flow shows a downward trend, that is, the current traffic diversion strategy can relieve the congestion on the congested road section, then it can be determined that the current congested road section can continue to maintain the traffic diversion strategy. If it is determined that the traffic flow shows an upward trend, that is, the current traffic diversion strategy cannot relieve the congestion on the congested road section, then determine the current passing time ratio corresponding to the current traffic diversion strategy. If the current passing time ratio is less than the preset threshold, then gradually increase the current passing time and adjust the traffic diversion strategy for traffic diversion control. If the current passing time ratio is greater than the preset threshold, then determine the alternative road sections corresponding to each outgoing road section in the congested direction. According to the distances between the alternative road sections and the congested road section and the traffic flows of the alternative road sections, determine the activation order of the alternative road sections to activate the alternative road sections in turn for traffic diversion. By dynamically adjusting the traffic diversion strategy and the activation order of the alternative road sections, this process can make more effective use of road resources, not only relieve the traffic pressure on the congested road section, but also improve the overall traffic efficiency and reduce the vehicle queuing time.

[0097] As Figure 2 shown, an embodiment of this specification provides a schematic structural diagram of a multi-lane traffic diversion control device. As Figure 2 known, in one or more embodiments of this specification, a multi-lane traffic diversion control device includes:

[0098] At least one processor; and,

[0099] A memory communicatively connected to the at least one processor; wherein,

[0100] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: execute any of the above-mentioned methods.

[0101] As Figure 3 shown, an embodiment of this specification provides a schematic structural diagram of a non-volatile storage medium. As Figure 3 known, in one or more embodiments of this specification, a non-volatile storage medium stores computer-executable instructions 301, and the computer-executable instructions 301 can: execute any of the above-mentioned methods.

[0102] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0103] The above description has been made of specific embodiments of this specification. In some cases, the actions or steps recited in the specification may be performed in an order different from that in the embodiments and still achieve the desired results. Additionally, the processes depicted in the accompanying drawings do not necessarily require the particular order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0104] The above is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, various changes and modifications can be made to one or more embodiments of this specification. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of one or more embodiments of this specification shall be included within the scope of this specification.

Claims

1. A method for diverting control of multiple lanes, characterized in that, The method includes: Dividing the current monitoring area based on road network related data to obtain multiple monitoring sub-areas, and determining the topological connection data corresponding to each monitoring sub-area according to the historical vehicle driving data of each monitoring sub-area; Performing clustering analysis on each monitoring sub-area according to the topological connection data, determining the target traffic characteristics of each monitoring sub-area, and determining the diversion traffic area corresponding to each monitoring sub-area based on the target traffic characteristics; Determining the current congested section according to the current vehicle driving data of each monitoring sub-area, and calculating the passing speeds of each lane in each direction within the current congested section, so as to divide and determine the congested direction and the non-congested direction; Determining the diversion traffic area corresponding to the current congested section, and determining the corresponding diversion strategy according to the passing speeds of the congested direction and the non-congested direction and the current vehicle driving data of the corresponding diversion traffic area; wherein, the diversion strategy includes: diversion path, diversion time; Inputting the passing speeds of each lane of the current congested section, the current vehicle driving data of the corresponding diversion traffic area, and the diversion strategy into a preset traffic flow prediction model, and adjusting the diversion strategy based on the output result for diversion control; Determining the topological connection data corresponding to each monitoring sub-area according to the historical vehicle driving data of each monitoring sub-area, specifically including: Obtaining the historical vehicle driving data of each monitoring sub-area, and identifying the incoming section and the outgoing section of each monitoring sub-area based on the driving direction data corresponding to each vehicle driving data and the boundary positions of each monitoring sub-area; Taking the incoming section and the outgoing section as the traversal starting nodes respectively, and traversing each section of the monitoring sub-area based on the traversal starting nodes and the preset traversal direction to obtain an incoming section sequence and an outgoing section sequence, and taking each section in the incoming section sequence and the outgoing section sequence as a node; wherein, the traversal direction is: clockwise direction or counterclockwise direction; Determining the adjacent sections of each node, and determining the section type of each node based on the basic road network data corresponding to the adjacent sections; wherein, the section type includes: diversion type, confluence type; Determining the vehicle driving frequency and the vehicle driving quantity between each node according to the historical vehicle driving data of each node, and determining the connection strength of each node according to the vehicle driving frequency, the vehicle driving quantity and the section type; Determining the connection paths between each constructed node based on the connection strength corresponding to each node and the sequence name corresponding to the node, and obtaining the topological connection data corresponding to each monitoring sub-area; Performing clustering analysis on each monitoring sub-area according to the topological connection data, and determining the target traffic characteristics of each monitoring sub-area, specifically including: Determining the adjacent nodes of each node in the monitoring sub-area based on the topological connection data, so as to construct a neighbor node set corresponding to each node; Successively obtain the adjacent nodes corresponding to each adjacent node in the set of neighbor nodes, and based on the intersection of the set of neighbor nodes and the adjacent nodes corresponding to each adjacent node, determine the common neighbor nodes corresponding to the adjacent nodes of the node and the node; Based on the historical vehicle travel data corresponding to the adjacent nodes of each node and the common neighbor nodes, construct the feature vectors corresponding to each node; Perform similarity clustering based on the feature vectors corresponding to each node to obtain multiple clustering clusters, and extract the common features of the nodes within each clustering cluster; Summarize the common features of each clustering cluster and determine the corresponding location distribution of each clustering cluster, so as to determine the target traffic features of each monitoring sub-region based on the common features of each clustering cluster and the corresponding location distribution; Determine the diversion traffic regions corresponding to each monitoring sub-region based on the target traffic features, specifically including: Based on the target traffic features of each monitoring sub-region, identify the traffic bottleneck data of each monitoring sub-region; wherein, the traffic bottleneck data includes: traffic peak period, congestion node range, road capacity; According to the traffic bottleneck data corresponding to each monitoring sub-region, determine the diversion capacity data corresponding to each monitoring sub-region; wherein, the diversion capacity data includes: diversion time, diversion capacity; Based on the diversion capacity data corresponding to the adjacent monitoring sub-regions of the monitoring sub-region, determine the optional diversion traffic regions corresponding to the diversion time and the traffic peak period; Determine the diversion capacity values of each optional diversion traffic region according to the diversion capacity of each optional diversion traffic region, so as to determine the diversion traffic regions corresponding to each monitoring sub-region based on the diversion capacity values; Divide the current monitoring area based on the road network related data to obtain multiple monitoring sub-regions, specifically including: Based on multiple data interfaces, obtain the road network related data of the current monitoring area; wherein, the road network related data includes: basic road network data, detector detection data, road operation data; According to the traffic network structure corresponding to the basic road network data and the preset regional boundary conditions, determine the initial monitoring sub-regions of multiple traffic levels corresponding to the current monitoring area; wherein the traffic levels include: intersection layer, intercity expressway layer, suburban express layer, living area road layer; the preset regional boundary conditions include: urban area level data, urban geographical boundary data, monitoring area limit data; Match the detector detection data and the operation data with the basic road network data according to the location information corresponding to the detector detection data and the operation data, so as to divide the detector detection data and the operation data into the corresponding initial monitoring sub-regions; Based on the detector detection data and the operation data, determine the internal traffic flow of each initial monitoring sub-region, so as to dynamically adjust the jurisdiction range of the initial monitoring sub-region according to the internal traffic flow to obtain multiple monitoring sub-regions; Determine a diversion traffic area corresponding to the current congested section, and determine a corresponding diversion strategy according to the traffic speeds in the congested direction and the non-congested direction and the current vehicle driving data in the corresponding diversion traffic area, specifically including: Determine a plurality of traffic areas to be diverted according to the diversion traffic area corresponding to the monitoring sub-area where the current congested section is located, and filter the plurality of traffic areas to be diverted according to the incoming road section or the outgoing road section within the preset range of the current congested section, so as to obtain a diversion traffic area corresponding to the current congested section; Based on the current vehicle driving data of the incoming road section and the outgoing road section corresponding to the non-congested direction in the diversion traffic area, determine the number of vehicles waiting to enter relatively in the non-congested direction; According to the traffic speed in the non-congested direction and the data of the vehicles waiting to enter relatively, determine the length of the waiting time that can be tolerated in the non-congested direction; Based on the traffic speed in the congested direction and the current vehicle driving data of the incoming road section and the outgoing road section corresponding to the non-congested direction in the diversion traffic area, determine the growth speed of the congestion queue in the congested direction; According to the growth speed of the congestion queue, the length of the waiting time that can be tolerated, and the road space information in the non-congested direction, determine the passing time ratio in the congested direction; If the passing time ratio is greater than a preset threshold, enable the alternative route corresponding to the congested direction in the diversion traffic area; Based on the output result, adjust the diversion strategy for diversion control, specifically including: If it is determined based on the output result that the traffic flow is in a downward trend, determine that the current diversion strategy is maintained for the current congested section; If it is determined that the traffic flow is in an upward trend, determine the current passing time ratio corresponding to the current diversion strategy; If the current passing time ratio is less than the preset threshold, gradually increase the current passing time, and adjust the diversion strategy for diversion control; If the current passing time ratio is greater than the preset threshold, determine the alternative sections corresponding to each outgoing road section in the congested direction; Based on the distances between the alternative sections and the congested section and the traffic flows of the alternative sections, determine the activation order of the alternative sections, so as to activate the alternative sections in sequence for diversion.

2. The multi-lane diversion control method according to claim 1, wherein, Before inputting the traffic speeds of each lane of the current congested section, the current vehicle driving data of the corresponding diversion traffic area, and the diversion strategy into a preset traffic flow prediction model, the method further includes: Collect the historical vehicle driving data corresponding to the historical diversion strategies in the current monitoring area, and divide the historical vehicle driving data corresponding to the historical diversion strategies based on a preset ratio to obtain training set data and validation set data; Input the training set data into an initial time series model for iterative training to obtain a trained time series model; Evaluate the trained time series model based on the validation set data, and adjust the trained time series model according to the evaluation result to obtain a preset traffic flow prediction model.

3. A multi-lane diversion control device, characterized in that, The device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to: execute the method according to any one of claims 1-2 above.

4. A non-volatile storage medium stores computer-executable instructions, characterized in that, The computer-executable instructions are capable of: executing the method according to any one of claims 1-2 above.

Images